Josef Sivic

Josef Sivic

Auto-generated profile, based on publicly available information

Josef Sivic

Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 October 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
CTCarl Toft
Carl Toft
WMWill Maddern
Will Maddern
ATAkihiko Torii
Akihiko Torii
LHLars Hammarstrand
Lars Hammarstrand
ESErik Stenborg
Erik Stenborg
TSTorsten Sattler
Torsten Sattler
Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds. Practical visual localization approaches need to be robust to a wide variety of viewing conditions, including day-night changes, as well as weather and seasonal variations, while providing highly accurate six degree-of-freedom (6DOF) camera pose estimates. In this paper, we extend three publicly available datasets containing images captured under a wide variety of viewing conditions, but lacking camera pose information, with ground truth pose information, making evaluation of the impact of various factors on 6DOF camera pose estimation accuracy possible. We also discuss the performance of state-of-the-art localization approaches on these datasets. Additionally, we release around half of the poses for all conditions, and keep the remaining half private as a test set, in the hopes that this will stimulate research on long-term visual localization, learned local image features, and related research areas. Our datasets are available at visuallocalization.net, where we are also hosting a benchmarking server for automatic evaluation of results on the test set. The presented state-of-the-art results are to a large degree based on submissions to our server.

13 October 2023 in ACS Catalysis
Verified
Journal Article
Open access
PKPetr Kouba
Petr Kouba
PKPavel Kohout
Pavel Kohout
FHFaraneh Haddadi
Faraneh Haddadi
ABAnton Bushuiev
Anton Bushuiev
RSRaman Samusevich
Raman Samusevich
SMStanislav Mazurenko
Stanislav Mazurenko
Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.

14 May 2014 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
OWOliver Whyte
Oliver Whyte
JSJosef Sivic
Josef Sivic
AZAndrew Zisserman
Andrew Zisserman

13 August 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
IRIgnacio Rocco
Ignacio Rocco
RARelja Arandjelovic
Relja Arandjelovic
JSJosef Sivic
Josef Sivic
We address the problem of determining correspondences between two images in agreement with a geometric model such as an affine, homography or thin-plate spline transformation, and estimating its parameters. The contributions of this work are three-fold. First, we propose a convolutional neural network architecture for geometric matching. The architecture is based on three main components that mimic the standard steps of feature extraction, matching and simultaneous inlier detection and model parameter estimation, while being trainable end-to-end. Second, we demonstrate that the network parameters can be trained from synthetically generated imagery without the need for manual annotation and that our matching layer significantly increases generalization capabilities to never seen before images. Finally, we show that the same model can perform both instance-level and category-level matching giving state-of-the-art results on the challenging PF, TSS and Caltech-101 datasets.

8 November 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
HTHajime Taira
Hajime Taira
MOMasatoshi Okutomi
Masatoshi Okutomi
TSTorsten Sattler
Torsten Sattler
MCMircea Cimpoi
Mircea Cimpoi
MPMarc Pollefeys
Marc Pollefeys
ATAkihiko Torii
Akihiko Torii
We seek to predict the 6 degree-of-freedom (6DoF) pose of a query photograph with respect to a large indoor 3D map. The contributions of this work are three-fold. First, we develop a new large-scale visual localization method targeted for indoor spaces. The method proceeds along three steps: (i) efficient retrieval of candidate poses that scales to large-scale environments, (ii) pose estimation using dense matching rather than sparse local features to deal with weakly textured indoor scenes, and (iii) pose verification by virtual view synthesis that is robust to significant changes in viewpoint, scene layout, and occlusion. Second, we release a new dataset with reference 6DoF poses for large-scale indoor localization. Query photographs are captured by mobile phones at a different time than the reference 3D map, thus presenting a realistic indoor localization scenario. Third, we demonstrate that our method significantly outperforms current state-of-the-art indoor localization approaches on this new challenging data. Code and data are publicly available.

16 March 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
YLYann Labbe
Yann Labbe
SZSergey Zagoruyko
Sergey Zagoruyko
IKIgor Kalevatykh
Igor Kalevatykh
ILIvan Laptev
Ivan Laptev
JCJustin Carpentier
Justin Carpentier
JSJosef Sivic
Josef Sivic
In this paper, we address the problem of visually guided rearrangement planning with many movable objects, i.e., finding a sequence of actions to move a set of objects from an initial arrangement to a desired one, while relying on visual inputs coming from a RGB camera. To do so, we introduce a complete pipeline relying on two key contributions. First, we introduce an efficient and scalable rearrangement planning method, based on a Monte-Carlo Tree Search exploration strategy. We demonstrate that because of its good trade-off between exploration and exploitation our method (i) scales well with the number of objects while (ii) finding solutions which require a smaller number of moves compared to the other state-of-the-art approaches. Note that on the contrary to many approaches, we do not require any buffer space to be available. Second, to precisely localize movable objects in the scene, we develop an integrated approach for robust multi-object workspace state estimation from a single uncalibrated RGB camera using a deep neural network trained only with synthetic data. We validate our multi-object visually guided manipulation pipeline with several experiments on a real UR-5 robotic arm by solving various rearrangement planning instances, requiring only 60 ms to compute the complete plan to rearrange 25 objects. In addition, we show that our system is insensitive to camera movements and can successfully recover from external perturbations.